AI Foundations · Chapter 2
What is Machine Learning?
A simple explanation of how machines learn patterns from data and use those patterns to make predictions.
Introduction
Machine Learning, often called ML, is a branch of Artificial Intelligence where computers learn patterns from data instead of being explicitly programmed for every rule.
Traditional software follows fixed instructions written by humans. Machine Learning systems look at examples, find patterns, and use those patterns to make predictions or decisions.
A Simple Example
Imagine you want to build a system that predicts house prices. Instead of writing every rule manually, you give the system historical data such as location, size, number of rooms, and previous sale prices.
The machine learning model studies that data and learns patterns like bigger houses usually cost more, location matters, and newer properties may have different values.
How Machine Learning Works
Most machine learning systems follow a simple process:
- Collect data
- Clean and prepare the data
- Train a model
- Test the model
- Use the model for predictions
Types of Machine Learning
There are three common types of machine learning:
- Supervised learning: the model learns from examples with correct answers.
- Unsupervised learning: the model finds hidden patterns without predefined answers.
- Reinforcement learning: the model learns by trying actions and receiving rewards or penalties.
Where Machine Learning is Used
- Fraud detection in banking
- Product recommendations
- Medical diagnosis support
- Email spam filtering
- Search ranking
- Image recognition
- Predictive maintenance
Machine Learning vs AI
Artificial Intelligence is the broader field. Machine Learning is one way to build AI systems.
In simple words: AI is the goal, and Machine Learning is one of the main techniques used to achieve that goal.
Common Misconceptions
Machine Learning does not automatically understand the world like humans do. It depends heavily on data quality, training examples, and proper evaluation.
A machine learning model can be powerful, but it can also make wrong predictions if the data is biased, incomplete, or not relevant.
Summary
Machine Learning helps computers learn from data and make predictions. It powers many real-world systems we use every day, from recommendations to fraud detection.
In the next chapter, we will explore Deep Learning and understand how neural networks changed modern AI.